Audio-visual robot command recognition: D-META'12 grand challenge
Proceedings of the 14th ACM international conference on Multimodal interaction
Continuous markov random fields for robust stereo estimation
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
Action recognition robust to background clutter by using stereo vision
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part I
Stereoscopic scene flow for robotic assisted minimally invasive surgery
MICCAI'12 Proceedings of the 15th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I
On the evaluation of scene flow estimation
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume 2
Consistent Binocular Depth and Scene Flow with Chained Temporal Profiles
International Journal of Computer Vision
Efficient and scalable 4th-order match propagation
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part I
Dense scene flow based on depth and multi-channel bilateral filter
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part III
Keep it simple and sparse: real-time action recognition
The Journal of Machine Learning Research
| Hi-index | 0.00 |
A simple seed growing algorithm for estimating scene flow in a stereo setup is presented. Two calibrated and synchronized cameras observe a scene and output a sequence of image pairs. The algorithm simultaneously computes a disparity map between the image pairs and optical flow maps between consecutive images. This, together with calibration data, is an equivalent representation of the 3D scene flow, i.e. a 3D velocity vector is associated with each reconstructed point. The proposed method starts from correspondence seeds and propagates these correspondences to their neighborhood. It is accurate for complex scenes with large motions and produces temporally-coherent stereo disparity and optical flow results. The algorithm is fast due to inherent search space reduction. An explicit comparison with recent methods of spatiotemporal stereo and variational optical and scene flow is provided.